Cybernetics And Systems Analysis logo
Editorial Board Announcements Abstracts Authors Archive
Cybernetics And Systems Analysis
International Theoretical Science Journal
-->

UDC 004.93'1
A.E. Sulavko1, P.S. Lozhnikov2, I.A. Kuprik3, A.E. Samotuga4


1 Omsk State Technical University, Omsk, Russia

sulavich@mail.ru

2 Omsk State Technical University, Omsk, Russia

lozhnikov@mail.ru

3 Omsk State Technical University, Omsk, Russia

ann.ik@mail.ru

4 Omsk State Technical University, Omsk, Russia

samotugasashok@mail.ru

PERSONAL IDENTIFICATION BASED ON THE INDIVIDUAL SONOGRAPHIC
PROPERTIES OF THE AURICLE USING CEPSTRAL ANALYSIS AND BAYES FORMULA

Abstract. A method of personality recognition by echographic parameters of the human ear has been developed on the basis of the “naive” Bayes classifier in two modes: biometric identification (EER= 0.0053) and biometric authentication (FRR= 0.0002 at FAR<= 0.0001), respectively. A device was developed for recording the biometric characteristics of the ear; a set of echographic data was collected from the ears of 75 subjects. The spectral and cepstral characteristics of the signals reflected from the ear canal were used as biometric parameters. Several window functions for constructing spectra and cepstrograms are considered. It has been established that more than 90% of “cepstral” features have a weak correlation dependence, which allows the use of a “naive” Bayesian classifier and at the same time obtaining highly accurate results of user recognition. The advantage of Bayesian classification is the possibility of robust fast learning of the identification system.

Keywords: cepstrograms, window Fourier transform, Bayes theorem, acoustic signal, pattern recognition, machine learning.



FULL TEXT

REFERENCES

  1. Akkermans T.H., Kevenaar T.A., Schobben D.W. Acoustic ear recognition. Advances in Biometrics: Proceedings of International Conference, ICB 2006 (Hong Kong, China, January 5–7, 2006). LNCS. 2006. Vol. 3832. Berlin; Heidelberg: Springer, 2006. P. 697–705.

  2. Epifantsev B.N., Lozhnikov P.S., Sulavko A.E. Algorithm for the identification of hypotheses in the space of uninformative features based on the sequential application of Bayes' formula. Interdisciplinary information service. Moscow: FGUP "VIMI”, 2013. N 2. P. 57–62.

  3. Lozhnikov P.S. Biometric protection of hybrid workflow [in Russian]. Novosibirsk: Publishing house of the SD RAS, 2017. 130 p.

  4. Vasilyev V.I., Sulavko A.E., Borisov R.V., Zhumazhanova S.S. Identification of the psychophysiological state of the user based on hidden monitoring in computer systems. Scientific and Technical Information Processing. 2018. Vol. 45, Iss. 6. P. 398–410. https://doi.org/10.3103/S0147688218060096.

  5. Tuyls P.T., Verbitskiy E., Ignatenko T., Schobben D., Akkermans T.H. Privacy-protected biometric templates: Acoustic ear identification. Proc. SPIE: Biometric Technology for Human Identification. 2004. Vol. 5404. P. 176–182. https://doi.org/10.1117/12.541882.

  6. Gao Y., Wang W., Phoha V.V., Sun W., Jin Z. EarEcho: Using ear canal echo for wearable authentication. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2019. Vol. 3, N 3. Article 81. https://doi.org/ 10.1145/3351239.




© 2021 Kibernetika.org. All rights reserved.